Objective : To find the nearest object (closer distance object) in the single camera image. But Image Contains multiple objects shown below:

Multiple Object in a Image

I searched in the net and found this formula to calculate the distance of object from camera

F = (P x D) / W Further Detail click on the Link

Is there any other better approach to find the nearest object in a image?

Thanks in Advance!!!

  • 1
    $\begingroup$ What components are you able to work with, and how much time/resources can you spend on this problem? If you are hoping to use an existing pre-trained YOLO model, and don't have any training data, just want to guess at nearest object, then something like your link is going to be best you can do. If you have time and ability to train a new model, you may be able to do better, but it could take a lot of effort to do so. $\endgroup$ Dec 26 '19 at 14:06
  • $\begingroup$ Also, do you have a specific use case that limits what types of object and their possible locations? If your camera is above ground level, with a horizontal horizon plus reasonable to assume all detected objects are on the ground (not the case in the image shown, but also not unusual assumption), then you could just rank objects by lowest point of bounding box. Other simplifications may apply in your case. $\endgroup$ Dec 26 '19 at 14:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.